Jinwei Hu
Scholar

Jinwei Hu

Google Scholar ID: lpql_8kAAAAJ
University of Liverpool
AI Safety and SecurityResponsible AIAI4ScienceExplainable AI
Google Scholar↗
Citations & Impact
All-time
Citations
272
 
H-index
7
 
i10-index
7
 
Publications
17
 
Co-authors
11
list available
Contact
No contact links provided.
Publications
21 items
Responsible Agentic AI Requires Explicit Provenance
2026
Cited
0
Safety-Constrained Reinforcement Learning with Post-Training Reachability Verification for Robot Navigation
2026
Cited
0
FragileFlow: Spectral Control of Correct-but-Fragile Predictions for Foundation Model Robustness
2026
Cited
0
PrefixGuard: From LLM-Agent Traces to Online Failure-Warning Monitors
2026
Cited
0
Where Do Prompt Perturbations Break Generation? A Segment-Level View of Robustness in LoRA-Tuned Language Models
2026
Cited
0
Spatiotemporal System Forecasting with Irregular Time Steps via Masked Autoencoder
2026
Cited
0
MIRAGE: Model-agnostic Industrial Realistic Anomaly Generation and Evaluation for Visual Anomaly Detection
2026
Cited
0
DDSA: Dual-Domain Strategic Attack for Spatial-Temporal Efficiency in Adversarial Robustness Testing
2026
Cited
0
Resume (English only)
Co-authors
11 total
Xiaowei Huang
Xiaowei Huang
Professor of Computer Science, University of Liverpool
Yi Dong
Yi Dong
University of Liverpool
Wenjie Ruan
Wenjie Ruan
Senior Lecturer, University of Exeter
Sibo Cheng
Sibo Cheng
Junior Professor, CEREA,ENPC, Institut Polytechnique de Paris
Guangliang Cheng
Guangliang Cheng
Reader (Associate Professor) in University of Liverpool
Rossella Arcucci
Rossella Arcucci
Associate Professor, Imperial College London
Co-author 7
Co-author 7
Co-author 8
Co-author 8